The coffee tasted like ash in her mouth. She'd been up since dawn, studying, working on essays, trying to prove herself. The rejection email was just another punch to the gut. She gripped the mug so tightly her knuckles whitened.

Her apartment, usually a haven, felt small and suffocating. Dust motes danced in the sunbeams that sliced through the blinds, each one mocking her efforts. She could feel the tremors in her hands, a persistent buzzing that wouldn't cease.

She considered calling her mom, but the thought of the disappointed voice on the other end was too much. Instead, she just sat there, the bitter coffee growing cold, and felt the familiar, heavy despair creeping in.

Emotion: worn out

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.12 Negative
PC2 (Disposition): -1.20

Role in Research

This story is one of 1,000 stories generated for the emotion worn out. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 worn out stories, after denoising with neutral dialogue baselines, produces the worn out emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the worn out vector is projected through the unembedding matrix.

Promoted:
😞0.265
😩0.234
η–²γ‚Œ0.226
que0.221
sighed0.221
Suppressed:
B-0.357
because-0.228
l-0.222
ΰ°­ΰ°Ώ-0.208
あくまで-0.208